Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Data-Driven Subsampling in the Presence of an Adversarial Actor (2401.03488v1)

Published 7 Jan 2024 in cs.LG, cs.CR, and eess.SP

Abstract: Deep learning based automatic modulation classification (AMC) has received significant attention owing to its potential applications in both military and civilian use cases. Recently, data-driven subsampling techniques have been utilized to overcome the challenges associated with computational complexity and training time for AMC. Beyond these direct advantages of data-driven subsampling, these methods also have regularizing properties that may improve the adversarial robustness of the modulation classifier. In this paper, we investigate the effects of an adversarial attack on an AMC system that employs deep learning models both for AMC and for subsampling. Our analysis shows that subsampling itself is an effective deterrent to adversarial attacks. We also uncover the most efficient subsampling strategy when an adversarial attack on both the classifier and the subsampler is anticipated.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (21)
  1. A. Svensson, “An introduction to adaptive qam modulation schemes for known and predicted channels,” Proceedings of the IEEE, vol. 95, no. 12, pp. 2322–2336, 2007.
  2. Y. Wang, W. Liu, and L. Fang, “Adaptive modulation and coding technology in 5g system,” in 2020 International Wireless Communications and Mobile Computing (IWCMC).   IEEE, 2020, pp. 159–164.
  3. O. A. Dobre, A. Abdi, Y. Bar-Ness, and W. Su, “Survey of automatic modulation classification techniques: classical approaches and new trends,” IET communications, vol. 1, no. 2, pp. 137–156, 2007.
  4. F. Meng, P. Chen, L. Wu, and X. Wang, “Automatic modulation classification: A deep learning enabled approach,” IEEE Transactions on Vehicular Technology, vol. 67, no. 11, pp. 10 760–10 772, 2018.
  5. T. J. O’Shea, T. Roy, and T. C. Clancy, “Over-the-air deep learning based radio signal classification,” IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 168–179, 2018.
  6. X. Zhang, X. Chen, Y. Wang, G. Gui, B. Adebisi, H. Sari, and F. Adachi, “Lightweight automatic modulation classification via progressive differentiable architecture search,” IEEE Transactions on Cognitive Communications and Networking, 2023.
  7. S. Ramjee, S. Ju, D. Yang, X. Liu, A. El Gamal, and Y. C. Eldar, “Ensemble wrapper subsampling for deep modulation classification,” IEEE Transactions on Cognitive Communications and Networking, vol. 7, no. 4, pp. 1156–1170, 2021.
  8. S. Ramjee, S. Ju, D. Yang, X. Liu, A. E. Gamal, and Y. C. Eldar, “Fast deep learning for automatic modulation classification,” arXiv preprint arXiv:1901.05850, 2019.
  9. Y. Shen, H. Yuan, P. Zhang, Y. Li, M. Cai, and J. Li, “A multi-subsampling self-attention network for unmanned aerial vehicle-to-ground automatic modulation recognition system,” Drones, vol. 7, no. 6, p. 376, 2023.
  10. I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015.
  11. M. Zolotukhin, P. Miraghaei, D. Zhang, and T. Hämäläinen, “On assessing vulnerabilities of the 5g networks to adversarial examples,” IEEE Access, vol. 10, pp. 126 285–126 303, 2022.
  12. M. Usama, M. Asim, J. Qadir, A. Al-Fuqaha, and M. A. Imran, “Adversarial machine learning attack on modulation classification,” in 2019 UK/China Emerging Technologies (UCET).   IEEE, 2019, pp. 1–4.
  13. B. Kim, Y. E. Sagduyu, K. Davaslioglu, T. Erpek, and S. Ulukus, “Over-the-air adversarial attacks on deep learning based modulation classifier over wireless channels,” in 2020 54th Annual Conference on Information Sciences and Systems (CISS).   IEEE, 2020, pp. 1–6.
  14. L. Zhang, S. Lambotharan, G. Zheng, G. Liao, A. Demontis, and F. Roli, “A hybrid training-time and run-time defense against adversarial attacks in modulation classification,” IEEE Wireless Communications Letters, 2022.
  15. I. Lee and W. Lee, “Uniqgan: Towards improved modulation classification with adversarial robustness using scalable generator design,” IEEE Transactions on Dependable and Secure Computing, 2023.
  16. T. Courtat and H. d. M. des Bourboux, “A light neural network for modulation detection under impairments,” in 2021 International Symposium on Networks, Computers and Communications (ISNCC).   IEEE, 2021, pp. 1–7.
  17. J. Krzyston, R. Bhattacharjea, and A. Stark, “Complex-valued convolutions for modulation recognition using deep learning,” in 2020 IEEE International Conference on Communications Workshops (ICC Workshops).   IEEE, 2020, pp. 1–6.
  18. N. Carlini and D. Wagner, “Towards evaluating the robustness of neural networks,” in 2017 ieee symposium on security and privacy (sp).   IEEE, 2017, pp. 39–57.
  19. V. Sathyanarayanan, P. Gerstoft, and A. El Gamal, “Rml22: Realistic dataset generation for wireless modulation classification,” IEEE Transactions on Wireless Communications, 2023.
  20. T. J. O’shea and N. West, “Radio machine learning dataset generation with gnu radio,” in Proceedings of the GNU Radio Conference, vol. 1, no. 1, 2016.
  21. N. Das, M. Shanbhogue, S.-T. Chen, F. Hohman, S. Li, L. Chen, M. E. Kounavis, and D. H. Chau, “Shield: Fast, practical defense and vaccination for deep learning using jpeg compression,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, pp. 196–204.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Abu Shafin Mohammad Mahdee Jameel (8 papers)
  2. Ahmed P. Mohamed (5 papers)
  3. Jinho Yi (2 papers)
  4. Aly El Gamal (52 papers)
  5. Akshay Malhotra (8 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now